ZipRecruiter

Log In

1

Vllm Jobs in Washington (NOW HIRING)

The Josef Group

AI Infrastructure Engineer

Chantilly, VA · On-site

$200 - $250/hr

Deploy and optimize self-hosted LLM inference servers (vLLM, Ollama, and similar). * Containerize AI workloads using Docker and orchestrate production environments with Kubernetes, including GPU ...

The Josef Group

AI Infrastructure Engineer

Chantilly, VA

$110K - $144K/yr

Deploy and optimize self-hosted LLM inference servers (vLLM, Ollama, and similar). * Containerize AI workloads using Docker and orchestrate production environments with Kubernetes, including GPU ...

Booz Allen Hamilton

AI Platform Engineer, Senior

Laurel, MD · On-site

$104K - $142K/yr

... vLLM or LiteLLM • Experience with agentic frameworks, including LangChain • Experience with vector databases and embedding systems • Experience with high-performance computing or distributed ...

Booz Allen Hamilton

AI Platform Engineer, Senior

Laurel, MD · On-site

$104K - $142K/yr

... vLLM or LiteLLM • Experience with agentic frameworks, including LangChain • Experience with vector databases and embedding systems • Experience with high-performance computing or distributed ...

CoreWeave

Solutions Architect

Washington, DC · On-site

$71 - $93.75/hr

... stack (vLLM, LangChain, LlamaIndex) • Working knowledge of cloud infrastructure for AI workloads, including GPU compute, high-performance networking, and storage • Experience using Slurm or ...

next page

Showing results 1-20

All JobsVllm JobsVllm Jobs in Washington

Vllm information

What is a vLLM?

VLLM stands for 'Virtual Large Language Model.' In the context of AI development, VLLM professionals work with optimized inference engines for large language models, enabling faster and more efficient deployment of AI models in production environments. Their responsibilities often include integrating LLMs into applications, optimizing model performance, and ensuring scalability for real-time use cases. They may also collaborate with data scientists and engineers to manage resources and streamline AI workflows.

How does a vLLM engineer typically collaborate with data scientists and product teams during model deployment?

VLLM Engineers work closely with data scientists to understand the specific requirements and fine-tuning needs of large-scale language models. They are often responsible for integrating these models into production systems, ensuring scalability and efficiency. Collaboration with product teams is crucial to align model capabilities with user needs and to troubleshoot real-world application challenges. Frequent communication and agile workflows are common, as updates or optimizations may be needed rapidly based on feedback from both teams.

What are the key skills and qualifications needed to thrive as a machine learning engineer working with vLLM, and why are they important?

To thrive as a Machine Learning Engineer specializing in vLLM (a high-throughput LLM inference library), you need a strong understanding of machine learning principles, deep learning frameworks, and experience with Python programming. Familiarity with tools like PyTorch, CUDA, distributed computing, and cloud platforms, as well as relevant certifications in ML or data engineering, is highly valuable. Strong problem-solving, collaboration, and communication skills are essential for optimizing model performance and integrating with cross-functional teams. These capabilities ensure effective deployment and scaling of large language models, driving innovation and efficiency in AI applications.

What is the difference between Vllm vs Data Analyst?

AspectVllmData Analyst
Required CredentialsTypically requires knowledge of machine learning, AI, and programming languages like Python or RRequires skills in statistics, Excel, SQL, and data visualization tools
Work EnvironmentOften in tech companies, research labs, or AI-focused teamsCommonly in business, finance, healthcare, and marketing sectors
Industry UsageEmerging role in AI and machine learning projectsEstablished role in data-driven decision making
Common Search/ComparisonVllm vs Data Analyst

The main difference between Vllm and Data Analyst lies in their focus and skill set. Vllm professionals specialize in AI and machine learning models, often working in tech environments, while Data Analysts focus on interpreting data to inform business decisions. Both roles require analytical skills, but Vllm roles demand programming and AI expertise, whereas Data Analysts emphasize statistical analysis and data visualization.

What are popular job titles related to Vllm jobs in Washington?

For Vllm jobs in Washington, the most frequently searched job titles are:

What job categories do people searching Vllm jobs in Washington look for?

The top searched job categories for Vllm jobs in Washington are:

What cities in Washington are hiring for Vllm jobs?

Cities in Washington with the most Vllm job openings:

Vllm jobs near you
Infographic showing various Vllm job openings in Washington as of August 2026, with employment types broken down into 95% Full Time, 3% Part Time, and 2% Contract. Highlights an 79% Physical, 5% Hybrid, and 16% Remote job distribution.

Junior AI Software Engineer [$212k/yr+] TS/SCI-FS Poly with Security Clearance

Annapolis Junction, MD • On-site

SYSTOLIC
Software Development • 51 - 200 employees
Learn more about SYSTOLICexternal

$212K/yr

Other

Posted 26 days ago

Job description

Candidates must already possess an active Top Secret/SCI w/ Full Scope Polygraph to be considered. Summary: • Build and maintain AI infrastructure, inference pipelines, and core services. • Utilize Python, Kubernetes, Helm, and AWS for foundation systems. • Procure, configure, and test LLM inference models utilizing vLLM, LiteLLM, Docker, and observability tools within CI/CD frameworks. Qualifications & Compensation: • Degree: Technical bachelor's degree or equivalent experience • Years of experience: 3+ years • Total Compensation: $212k+ yearly Job Description: • Procure, configure, and test new inference models, preparing them for deployment. • Develop in-house services and techniques to guarantee continual high-quality inference service. • Work with model vendor teams to create reliable pipelines for closed-source model usage. • Establish solid infrastructure for services and integrate LLM-powered tools for user needs. • Utilize experience with Python, Kubernetes, Helm, and cloud service providers such as AWS. • Apply familiarity with Argo CD/CI/CD frameworks, vLLM, LiteLLM, Docker, Elastic, and Grafana/Prometheus. About SYSTOLIC: SYSTOLIC is dedicated to giving our employees the best possible company experience so that they can focus on providing outstanding support to their customer’s mission. Our company is founded on integrity, enthusiasm, and a relentless commitment to supporting the Intelligence Community. You can learn more about us and submit an application to be considered against our current and future openings at https://systolic.com. To learn about our compensation ranges, visit our Pay Transparency page at: https://systolic.com/pay-transparency

Apply